Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.1225. Min Act: -0.0000

Data Index: 817889 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.9665. Min Act: -0.0000

Data Index: 508065 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.7381. Min Act: -0.0001

Data Index: 378191 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.5729. Min Act: -0.0000

Data Index: 714259 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.4727. Min Act: -0.0000

Data Index: 226851 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.4592. Min Act: -0.0000

Data Index: 866125 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.4049. Min Act: -0.0000

Data Index: 867316 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.3943. Min Act: -0.0000

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2943. Min Act: -0.0001

Data Index: 675192 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.3726. Min Act: -0.0000

Data Index: 1307492 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.3516. Min Act: -0.0000

Data Index: 688194 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2716. Min Act: -0.0000

Data Index: 447892 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.3334. Min Act: -0.0000

Data Index: 428476 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2494. Min Act: -0.0000

Data Index: 493397 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.3951. Min Act: -0.0000

Data Index: 635198 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2871. Min Act: -0.0000

Data Index: 466009 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2541. Min Act: -0.0000

Data Index: 809882 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2491. Min Act: -0.0001

Data Index: 331974 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.3443. Min Act: -0.0000

Data Index: 107312 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 2.1225. Min Range: -2.1225

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1257513 (C4 (Web Text))

Max Activating Token Index: 162